NVIDIA/SkillSpector
Security scanner for AI agent skills
- Chart
- Not on a chart right now
- Stars
- 26.8k
What it is
A security scanner that checks AI agent skills used by Claude Code, Codex, and MCP for vulnerabilities, malicious patterns, prompt injection, data exfiltration, and supply-chain risks before installation.
Who it is for
Developers and security teams who want to verify the safety of third-party agent skills or MCP servers before installing them.
Why it is trending
It gained 6,127 stars today, reaching 26,549 total stars, following the v2.13.6 release on November 16, 2026. It combines fast static analysis with optional LLM semantic evaluation, covering 71 vulnerability patterns and live CVE lookups via OSV.dev.
Main features
- Scans Git repos, URLs, zip archives, directories, and single files
- Detects 71 vulnerability patterns across 17 categories including prompt injection and MCP tool poisoning
- Queries OSV.dev for live CVE vulnerability lookups with offline fallback
- Outputs Terminal, JSON, Markdown, and SARIF reports with 0-100 risk scores
Summarized on November 17, 2026 from the README and repository data. It can be wrong; check the source before relying on it. Report a wrong summary